Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.1392. Min Act: -0.0000

Data Index: 1545621 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.0341. Min Act: -0.0000

Data Index: 1645182 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.2055. Min Act: -0.0000

Data Index: 1191307 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.9926. Min Act: -0.0000

Data Index: 735607 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.2694. Min Act: -0.0000

Data Index: 1980826 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.0341. Min Act: -0.0001

Data Index: 312490 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 5.4039. Min Range: -5.4039

Max Act: 5.4039. Min Act: -0.0000

Data Index: 1195024 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.8636. Min Act: -0.0000

Data Index: 1499347 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.8625. Min Act: -0.0000

Data Index: 343930 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.9646. Min Act: -0.0001

Data Index: 873662 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.7312. Min Act: -0.0000

Data Index: 327737 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.7183. Min Act: -0.0000

Data Index: 1404348 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.8843. Min Act: -0.0000

Data Index: 1049947 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.5351. Min Act: -0.0000

Data Index: 658887 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.3563. Min Act: -0.0000

Data Index: 701515 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.6646. Min Act: -0.0000

Data Index: 1706999 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.6248. Min Act: -0.0000

Data Index: 823174 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.8114. Min Act: -0.0000

Data Index: 1590003 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.7663. Min Act: -0.0000

Data Index: 1162497 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 5.4039. Min Range: -5.4039

Max Act: 4.5444. Min Act: -0.0000

Data Index: 862235 (The Pile)

Max Activating Token Index: 268